Meeba Brain MCP server
io.github.meemoprasad/meeba-brainmeemoprasadstreamable-httpv1.0.1Scanned
Repository knowledge graph MCP server for codebase understanding and debugging.
5 tools: 5 only read.
- Reads private data · 3
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Meeba Brain MCP server can do
The Meeba Brain MCP server is published by the GitHub account meemoprasad. It has 5 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
3 tools read private data (search_code, get_callers and get_dependencies).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 21, 2026, version 1.0.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
5 tools
Only reads 5Show 5 read-only tools
get_calleesEvery function/method the given function calls -- what it depends on to do its job.No findings
Why it is in this group
- The name "get_callees" says "get": a word for reading.
Description, as the server wrote it Every function/method the given function calls -- what it depends on to do its job. Use this to understand a function's behavior by seeing what it delegates to, before assuming what it does from its name alone.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
get_callersEvery place in this repo that calls the given function or method -- a COMPLETE list from the parsed call graph, not a best-effort guess.Reads private dataNo findings
Why it is in this group
- The name "get_callers" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "repo": it reads repositories.
Description, as the server wrote it Every place in this repo that calls the given function or method -- a COMPLETE list from the parsed call graph, not a best-effort guess. Use this before renaming/changing a function's signature, or when you need to understand a function's blast radius before modifying it.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
get_dependenciesWhat a specific file imports/depends on.Reads private dataNo findings
Why it is in this group
- The name "get_dependencies" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "file": it reads files.
- private-dataThe input names a file (input.file_path), and the tool reads: it reads files.
Description, as the server wrote it What a specific file imports/depends on. Use this to understand a file's place in the codebase before assuming what's available to it, or before moving/refactoring it.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
get_symbol_definitionFinds where a function, class, or method is actually defined in this repo -- exact file, line range, and signature-relevant metadata (async, decorators, docstring if present).No findings
Why it is in this group
- The name "get_symbol_definition" says "get": a word for reading.
Description, as the server wrote it Finds where a function, class, or method is actually defined in this repo -- exact file, line range, and signature-relevant metadata (async, decorators, docstring if present). Use this before assuming a symbol's location/signature from memory or from a similarly-named symbol in a different file.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
search_codeHybrid semantic + keyword search over the connected repository's actual indexed content.Reads private dataNo findings
Why it is in this group
- The name "search_code" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "repository": it reads repositories.
Description, as the server wrote it Hybrid semantic + keyword search over the connected repository's actual indexed content. Use this for open-ended questions ("where is rate limiting implemented?", "how are uploads validated?") where you don't already know an exact symbol or file name -- for those, use get_symbol_definition or get_dependencies instead, they're more precise.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.
- Reads private data3
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:27 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 0
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http meeba-brain https://meeba-context-mcp-469248886325.us-central1.run.app/mcpclaude mcp add --transport http meeba-brain https://meeba-context-mcp-469248886325.us-central1.run.app/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__meeba-brain__search_code",
"mcp__meeba-brain__get_symbol_definition",
"mcp__meeba-brain__get_callers",
"mcp__meeba-brain__get_callees",
"mcp__meeba-brain__get_dependencies"
],
"ask": [],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as meeba-brain. Review it before you use it.
Capability tags behind 3 rules
- mcp__meeba-brain__search_code private-data
- mcp__meeba-brain__get_callers private-data
- mcp__meeba-brain__get_dependencies private-data
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.meemoprasad/meeba-brain/verify?hash=5623a81d5c7c7d7998cf82158efc89818603bae4acf9ce34aff691358b43eb61" | jq -e '.changed == false'Pinned hash 5623a81d5c7c, from Nov 21, 2026, 07:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.meemoprasad/meeba-brain/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.meemoprasad/meeba-brain)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:40 UTC.
Meeba Brain MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Meeba Brain MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the Meeba Brain MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Meeba Brain MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Meeba Brain MCP server have?
- 5 tools: 5 read. search_code, get_symbol_definition, get_callers, get_callees and get_dependencies.
Does the Meeba Brain MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Meeba Brain MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Meeba Brain MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.